A Cognitively Inspired System Architecture for the Mengshi Cognitive Vehicle

  • Xinyu Zhang
  • Mo Zhou
  • Huaping LiuEmail author
  • Amir Hussain


This paper introduces the functional system architecture of the Mengshi intelligent vehicle, winner of the 2018 World Intelligent Driving Challenge (WIDC). Different from traditional smart vehicles, a cognitive module is introduced in the system architecture to realise the transition from perception to decision-making. This is shown to enhance the practical utility of the smart vehicle, enabling safe and robust driving in different scenes. The collaborative work of hardware and software systems is achieved through multi-sensor fusion and artificial intelligence (AI) technologies, including novel use of deep machine learning and context-aware scene analysis to select optimal driving strategies. Experimental results using both robustness tests and road tests confirm that the Mengshi intelligent vehicle is reliable and robust in challenging environments. This paper describes the major components of this cognitively inspired architecture and discusses the results of the 2018 WIDC.


Cognitive vehicle Autonomous driving Driving scene construction Cross-modal transfer 


Funding Information

This work was supported by the National High Technology Research and Development Program (“973”Program) of China under Grant No. 2016YFB0100903, National High Technology Research and Development Program of China under Grant No. 2018YFE0204300, Beijing Municipal Science and Technology Commission special major under Grant No. D171100005017002, National Natural Science Foundation of China under Grant No. U1664263.

Compliance with Ethical Standards

Conflict of Interest

The authors declare that they have no conflict of interest.

Ethical Approval

This article does not contain any studies with human participants or animals performed by any of the authors.

Informed Consent

Informed consent was obtained from all individual participants included in the study.


  1. 1.
    Zhang X Y, Gao H B, Guo M. A study on key technologies of unmanned driving. Caai Trans Intel Technol 2016;1(1):4–13.CrossRefGoogle Scholar
  2. 2.
    Marghi Y, Towhidkhah F, Gharibzadeh S. Human brain function in path planning: a task study. Cogn Comput 2017;9(1):136–149.CrossRefGoogle Scholar
  3. 3.
    Heide A, Henning K. The cognitive car: a roadmap for research issues in the automotive sector. Annu Rev Control 2006;30(2):197–203.CrossRefGoogle Scholar
  4. 4.
    Themes for a new research centre (Themen fur ein neues DFG Forschungszentrum definiert). Informationen fur die Wissenschaft No.8. Deutsche Forschungsgemeins-chaft e.V Bonn, 2004.Google Scholar
  5. 5.
    Czubenko M, Kowalczuk Z, Ordys A. Autonomous driver based on an intelligent system of decision-making. Cogn Comput 2015;7(5):569–581.CrossRefGoogle Scholar
  6. 6.
    Yue L. Deep learning based scene parsing algorithm for intelligent vehicle. Beijing: Beijing Forestry University; 2016.Google Scholar
  7. 7.
    Amparore E, Beccuti M, Collina S. 2015. Cognitive systems in intelligent vehicles - a new frontier for autonomous driving, International conference on informatics in control, automation and robotics, pp 817–822.Google Scholar
  8. 8.
    Li L, Wen D, Zheng N N, Shen L C. Cognitive cars: a new frontier for ADAS research. IEEE Trans Intell Transp Syst 2012;13(1):395–407.CrossRefGoogle Scholar
  9. 9.
    Candamo J. Understanding transit scenes: a survey on human behavior-recognition algorithms. IEEE Trans Intell Transp Syst 2010;11(1):206–224.CrossRefGoogle Scholar
  10. 10.
    Thrun S, Montemerlo M, Dahlkamp H. 2006. Stanley: the robot that won the DARPA grand challenge. The 2005 DARPA grand challenge, pp 1–43.Google Scholar
  11. 11.
    Levinson J, Askeland J, Becker J. 2011. Towards fully autonomous driving: systems and algorithms. Intelligent Vehicles Symposium, pp 163–168.Google Scholar
  12. 12.
    Ziegler J, Bender P, Schreiber M. Making bertha drive: an autonomous journey on a historic route. Int Transp Syst Magazine 2014;6(2):8–20.CrossRefGoogle Scholar
  13. 13.
    Chen L. The core basic scientific question of new generation artificial intelligence: the relation between cognition and computing. Think Tank Viewpoint 2018;33(10):1104–1106.Google Scholar
  14. 14.
    Song Y, Li Q, Kang Y. Conjugate unscented FastSLAM for autonomous mobile robots in large-scale environments. Cogn Comput 2014;6(3):496–509.CrossRefGoogle Scholar
  15. 15.
    Tu Z, Zheng A, Yang E, Luo B, Hussain A. A biologically inspired vision-based approach for detecting multiple moving objects in complex outdoor scenes. Cogn Comput 2015;7(5):539–551.CrossRefGoogle Scholar
  16. 16.
    Chen S, Zhang S, Shang J. Brain-inspired cognitive model with attention for self-driving cars. IEEE Trans Cogn Dev Syst 2017;99:1–13.Google Scholar
  17. 17.
    Zhao J H, Zhang X Y, Gao H B, Zhou M. 2018. Object detection based on hierarchical multi-view proposal network for autonomous driving, 2018 international joint conference on neural networks (IJCNN), pp 1–6.Google Scholar
  18. 18.
    Zhang K, Liu H, Deng X, Sun F. Radar-image cross-modal retrieval for outdoor mobile robots. Proc. of cognitive systems and information processing; 2018.Google Scholar
  19. 19.
    Liu H, Sun F, Fang B, Zhang X. Robotic room-level localization using multiple sets of sonar measurements. IEEE Trans Instrum Meas 2017;66(1):2–13.CrossRefGoogle Scholar
  20. 20.
    Li Y B, Niu L, Tong H. The design about smart car autopilot based on Global Positioning System. Automotive Electronics 2018;11:61–63.Google Scholar
  21. 21.
    Liu W, Zhang K, Zhang G S, Chi C. Development of vehicle dynamic state estimation in linear region based on wheel speed information. Automobile Applied Technology 2016;9:55–58.Google Scholar
  22. 22.
    Yu Y F, Zhao H J, Cui J S, Zha H B. Road structural feature based monocular visual localization for intelligent vehicle. Acta Automatica Sinica 2017;43(5):725–734.Google Scholar
  23. 23.
    Yu Z P, Zhang R X, Xiong L, Huang C J. Dynamic control for unmanned skid-steering vehicle with conditional integartors. J Mech Eng 2017;53(14):29–38.CrossRefGoogle Scholar
  24. 24.
    Wu T, Zhao J Y, Zhang Z L, Lu Z Y, Chang Z J. On current status and development tendency of vehicle visual odometer. Electronics Optics & Control 2017;24(10):69–74.Google Scholar
  25. 25.
    Zhao T T, Chen W P, Gu Y F. Design of automatic cruise unmanned ground vehicle based on environmental perception. Radio Eng 2017;47(10):73–78.Google Scholar
  26. 26.
    Mahmud M, Kaiser M S, Hussain A, Vassanelli S. Applications of deep learning and reinforcement learning to biological data. IEEE Trans Neural Netw Learn Syst 2018;29(6):2063–2079.CrossRefGoogle Scholar
  27. 27.
    Xiong F, Sun B, Yang X, Qiao H, Huang K, Hussain A, Liu Z. Guided policy search for sequential multitask learning. IEEE Trans Syst, Man, Cybern: Syst 2018;PP(99):1–11.Google Scholar
  28. 28.
    Scardapane S, Comminiello D, Hussain A, Uncini A. Group sparse regularization for deep neural networks. Elsevier Neurocomputing 2017;241:81–89.CrossRefGoogle Scholar
  29. 29.
    Zhang L, Liu Z, Zhang S, Yang X, Qiao H, Huang K, Hussain A. Cross-modality interactive attention network for multispectral pedestrian detection. Elsevier Information Fusion 2018;50:20–29.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  1. 1.State Key Laboratory of Automotive Safety and EnergyTsinghua UniversityBeijingChina
  2. 2.Department of Computer Science and TechnologyTsinghua UniversityBeijingChina
  3. 3.School of ComputingEdinburgh Napier UniversityEdinburghUK

Personalised recommendations